Contact Information

Addess: 140 Governors Dr.
Amherst, MA - 01002
Room 266
Email:    fmgarcia [at] cs [dot] umass [dot] edu
LinkedIn: Click for profile
Resume: Click for cv

Profile Picture

Francisco M. Garcia

I am a Ph.D. candidate in College of Information and Computer Science at the University of Massachusetts - Amherst. I am a member of the Autonomous Learning Laboratory (ALL) , co-directed by my adviser, Philip Thomas, and Sridhar Mahadevan. I completed my M.S. in 2015 at UMass Amherst, and my B.S. at the University of the Sciences in Philadelphia.

My research focus is in Reinforcement Learning, and I am interested in machine learning, optimization, planning and robotics.

Professional Experience

Profile Picture
Profile Picture
Profile Picture
Profile Picture
Profile Picture


  • Francisco M. Garcia, Bruno C. da Silva, Philip Thomas. A Compression-Inspired Framework for Macro Discovery. 2019, Workshop on Reinforcement Learning in Games, AAAI. pdf

  • Francisco M. Garcia, Philip Thomas. A Meta-MDP Approach to Exploration for Lifelong Reinforrcement Learning. 2019, Workshop on Reinforcement Learning in Games, AAAI. pdf

  • Giguere Stephen, Francisco M. Garcia, Shridar Mahadevan. A Manifold Approach to Learning Mutually Orthogonal Subspaces. 2016, pdf

  • Kai Ninomiya, Mubbasir Kapadia, Alexander Shoulson, Francisco M. Garcia and Norman I. Badler, Planning Approaches to Constraint-aware Navigation in Dynamic Environments, 2014 Computer Animation and Virtual Worlds pdf

  • Francisco M. García, Mubbasir Kapadia and Norman I. Badler, GPU-based Dynamic Search on Adaptive Resolution Grids, 2014 IEEE International Conference on Robotics and Automation, Hong Kong, China pdf, video

  • Mubbasir Kapadia, Kai Ninomiya, Alexander Shoulson, Francisco M. García and Norman I. Badler, Constraint Aware Navigation in Dynamic Environments, ACM SIGGRAPH conference on Motion in Games (MIG '13) pdf, video

  • Mubbasir Kapadia, Francisco M. García, and Norman I. Badler. Dynamic Search on the GPU. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013 pdf, video

  • Mubbasir Kapadia, Alejandro Porres, Francisco M. García, Vivek Reddy, Nuria Pelechano, and Norman I. Badler. Multi-Domain Real-time Planning in Dynamic Environments. ACM SIGGRAPH/EUROGRAPHICS Symposium of Computer Animation, 2013 pdf, video

  • Shoulson, Alexander, Francisco M. García, Matthew Jones, Robert Mead & Norman I. Badler (2011). “Parameterizing Behavior-Trees”. Jan M. Allbeck & Petros Faloutsos (Eds.). Fourth International Conference on Motion in Games (MIG) pdf